options

Experiment Quality

orig_defaultgcc_defaultarmclang_1gcc_1

[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.

[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.

[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.

[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.

[ 2.99 / 3 ] Architecture specific option -mcpu is used

[ 3.00 / 3 ] Architecture specific option -mcpu is used

[ 2.99 / 3 ] Architecture specific option -mcpu is used

[ 3.00 / 3 ] Architecture specific option -mcpu is used

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations and -fno-omit-frame-pointer is present

-fno-omit-frame-pointer improves the accuracy of callchains found during the application profiling.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations and -fno-omit-frame-pointer is present

-fno-omit-frame-pointer improves the accuracy of callchains found during the application profiling.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations and -fno-omit-frame-pointer is present

-fno-omit-frame-pointer improves the accuracy of callchains found during the application profiling.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations and -fno-omit-frame-pointer is present

-fno-omit-frame-pointer improves the accuracy of callchains found during the application profiling.

[ 3 / 3 ] Optimization level option is correctly used

[ 3 / 3 ] Optimization level option is correctly used

[ 3 / 3 ] Optimization level option is correctly used

[ 3 / 3 ] Optimization level option is correctly used

[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.02 % of the execution time)

To have a representative profiling, it is advised that the category "Others" represents less than 20% of the execution time in order to analyze as much as possible of the user code

[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.01 % of the execution time)

To have a representative profiling, it is advised that the category "Others" represents less than 20% of the execution time in order to analyze as much as possible of the user code

[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.02 % of the execution time)

To have a representative profiling, it is advised that the category "Others" represents less than 20% of the execution time in order to analyze as much as possible of the user code

[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.02 % of the execution time)

To have a representative profiling, it is advised that the category "Others" represents less than 20% of the execution time in order to analyze as much as possible of the user code

[ 4 / 4 ] Application profile is long enough (151.79 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 4 / 4 ] Application profile is long enough (153.11 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 4 / 4 ] Application profile is long enough (151.74 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 4 / 4 ] Application profile is long enough (153.31 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.

[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.

[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.

[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.

Code Quality

orig_defaultgcc_defaultarmclang_1gcc_1

[ 4 / 4 ] CPU activity is good

CPU cores are active 95.85% of time

[ 4 / 4 ] CPU activity is good

CPU cores are active 94.97% of time

[ 4 / 4 ] CPU activity is good

CPU cores are active 95.81% of time

[ 4 / 4 ] CPU activity is good

CPU cores are active 94.91% of time

[ 4 / 4 ] Affinity is good (99.87%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 4 / 4 ] Affinity is good (99.67%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 4 / 4 ] Affinity is good (99.82%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 4 / 4 ] Affinity is good (99.65%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 3 / 3 ] Functions mostly use all threads

Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (2.86%)

[ 3 / 3 ] Functions mostly use all threads

Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (2.39%)

[ 3 / 3 ] Functions mostly use all threads

Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (2.85%)

[ 3 / 3 ] Functions mostly use all threads

Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (2.28%)

[ 3 / 3 ] Cumulative Outermost/In between loops coverage (15.80%) lower than cumulative innermost loop coverage (78.58%)

Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex

[ 3 / 3 ] Cumulative Outermost/In between loops coverage (14.04%) lower than cumulative innermost loop coverage (81.34%)

Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex

[ 3 / 3 ] Cumulative Outermost/In between loops coverage (15.82%) lower than cumulative innermost loop coverage (78.49%)

Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex

[ 3 / 3 ] Cumulative Outermost/In between loops coverage (14.08%) lower than cumulative innermost loop coverage (81.34%)

Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex

[ 4 / 4 ] Threads activity is good

On average, more than 95.81% of observed threads are actually active

[ 4 / 4 ] Threads activity is good

On average, more than 94.93% of observed threads are actually active

[ 4 / 4 ] Threads activity is good

On average, more than 95.77% of observed threads are actually active

[ 4 / 4 ] Threads activity is good

On average, more than 94.88% of observed threads are actually active

[ 2 / 2 ] Less than 10% (0.00%) is spend in BLAS2 operations

BLAS2 calls usually could make a poor cache usage and could benefit from inlining.

[ 2 / 2 ] Less than 10% (0.00%) is spend in BLAS2 operations

BLAS2 calls usually could make a poor cache usage and could benefit from inlining.

[ 2 / 2 ] Less than 10% (0.00%) is spend in BLAS2 operations

BLAS2 calls usually could make a poor cache usage and could benefit from inlining.

[ 2 / 2 ] Less than 10% (0.00%) is spend in BLAS2 operations

BLAS2 calls usually could make a poor cache usage and could benefit from inlining.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (78.58%)

If the time spent in analyzed innermost loops is less than 15%, standard innermost loop optimizations such as vectorisation will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (81.34%)

If the time spent in analyzed innermost loops is less than 15%, standard innermost loop optimizations such as vectorisation will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (78.49%)

If the time spent in analyzed innermost loops is less than 15%, standard innermost loop optimizations such as vectorisation will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (81.34%)

If the time spent in analyzed innermost loops is less than 15%, standard innermost loop optimizations such as vectorisation will have a limited impact on application performances.

[ 3 / 3 ] Less than 10% (0.17%) is spend in BLAS1 operations

It could be more efficient to inline by hand BLAS1 operations

[ 3 / 3 ] Less than 10% (0.16%) is spend in BLAS1 operations

It could be more efficient to inline by hand BLAS1 operations

[ 3 / 3 ] Less than 10% (0.16%) is spend in BLAS1 operations

It could be more efficient to inline by hand BLAS1 operations

[ 3 / 3 ] Less than 10% (0.16%) is spend in BLAS1 operations

It could be more efficient to inline by hand BLAS1 operations

[ 2 / 2 ] Less than 10% (0.01%) is spend in Libm/SVML (special functions)

[ 2 / 2 ] Less than 10% (0.01%) is spend in Libm/SVML (special functions)

[ 2 / 2 ] Less than 10% (0.00%) is spend in Libm/SVML (special functions)

[ 2 / 2 ] Less than 10% (0.00%) is spend in Libm/SVML (special functions)

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.80%), representing an hotspot for the application

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (23.41%), representing an hotspot for the application

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.75%), representing an hotspot for the application

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (23.34%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (94.37%)

If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (95.38%)

If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (94.31%)

If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.

[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (95.42%)

If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.

Loops Overview

Analysisr0r1r2r3
Loop Computation IssuesPresence of expensive FP instructions2323
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA0101
Presence of a large number of scalar integer instructions3323
Control Flow IssuesPresence of 2 to 4 paths1000
Presence of more than 4 paths0101
Non-innermost loop1010
Data Access IssuesPresence of constant non-unit stride data access8989
Presence of indirect access1111
Vectorization RoadblocksPresence of 2 to 4 paths1000
Presence of more than 4 paths1111
Non-innermost loop1010
Presence of constant non-unit stride data access8989
Presence of indirect access1111
×